CT图像纹理分析对小于10 mm纯磨玻璃结节侵袭性的诊断价值

doi:10.3877/cma.j.issn.1674-0785.2019.05.009

目的

探讨CT图像纹理分析对小于10 mm纯磨玻璃结节的侵袭性的诊断价值。

方法

收集2015年1月至2017年3月在无锡市人民医院行手术治疗的<10 mm纯磨玻璃结节148例，其中浸润前病变组73例，浸润性病变组75例，运用ImageJ软件对其图像进行纹理特征提取，并找出2组有差别的参数，运用Spearman相关性分析进行特征性降维，找出独立的预测因子，再运用受试者工作特征曲线评价独立预测因子的诊断效能。

结果

影像特征提取得到31个CT图像纹理特征参数，差异有统计学意义的参数有19个，经降维处理最终得到3个与肺腺癌浸润性相关的独立参数，即角二阶矩、相关性和逆差矩，曲线下面积分别为0.715、0.720、0.736。

结论

CT图像纹理分析对判断早期肺腺癌的浸润性有一定的诊断价值。

关键词: 纹理分析, 肺肿瘤, 肿瘤浸润, 体层摄影术，X线计算机

Objective

To assess the value of CT texture analysis in diagnosing the invasiveness of lung adenocarcinoma manifesting as pure ground glass nodules less than 10 mm.

Methods

The preoperative CT data of 148 patients manifesting as pure ground glass nodules less than 10 mm who underwent operation were analyzed retrospectively. Among 148 cases of pure ground glass nodules, 73 were preinvasive lesions and 75 were invasive lesions of lung adenocarcinoma. ImageJ software was used to extract the texture features of the images and then the parameters that differed significantly between the preinvasive lesions and invasive lesions were identified. Spearman correlation analysis was used for feature dimension reduction, and then independent predictors were selected out. Receiver operator characteristic curve was then used to evaluate the diagnostic efficiency of independent predictors.

Results

Among 31 parameters of texture feature obtained by CT feature extraction, 19 statistically differed between the two groups. Three independent parameters related to lung adenocarcinoma invasiveness were obtained after dimension reduction, which were angular second moment, contrast, and inverse difference moment. The areas under the curves of the three parameters for diagnosing the invasiveness of early lung adenocarcinoma were 0.715, 0.720, and 0.736, respectively.

Conclusion

CT texture analysis is helpful in the diagnosis of invasiveness of early lung adenocarcinoma.

Key words: Texture analysis, Lung neoplasms, Neoplasm invasiveness, Tomography, X-ray computed

图1 浸润前病变和浸润性病变角二阶矩、相关性和逆差矩的受试者工作特征曲线

表1 浸润前病变组和浸润性病变组有差异的特征性参数（±s）

病变	角二阶矩	相关性	逆差矩
浸润前病变	0.013±0.005	0.003±0.002	0.149±0.008
浸润性病变	0.004±0.002	0.002±0.001	0.092±0.051
双侧P值	<0.001	<0.001	<0.001

表1 浸润前病变组和浸润性病变组有差异的特征性参数（±s）

病变	角二阶矩	相关性	逆差矩
浸润前病变	0.013±0.005	0.003±0.002	0.149±0.008
浸润性病变	0.004±0.002	0.002±0.001	0.092±0.051
双侧P值	<0.001	<0.001	<0.001

表2 浸润前病变和浸润性病变曲线下面积及其95%可信区间

检验结果变量	曲线下面积	标准误^a	双侧P值^b	95%可信区间
角二阶矩	0.715	0.042	<0.001	0.633~0.797
相关性	0.72	0.042	<0.001	0.638~0.801
逆差矩	0.736	0.04	<0.001	0.657~0.815

表2 浸润前病变和浸润性病变曲线下面积及其95%可信区间

检验结果变量	曲线下面积	标准误^a	双侧P值^b	95%可信区间
角二阶矩	0.715	0.042	<0.001	0.633~0.797
相关性	0.72	0.042	<0.001	0.638~0.801
逆差矩	0.736	0.04	<0.001	0.657~0.815

1	Travis WD, Brambilla E, Noguchi M, et al. International association for the study of lung cancer/american thoracic society/european respiratory society international multidisciplinary classification of lung adenocarcinoma [J]. J Thorac Oncol, 2011, 6(2): 244-285.
2	Lederlin M, Revel MP, Khalil A, et al. Management strategy of pulmonary nodule in 2013 [J]. Diagn Interv Imaging, 2013, 94(11): 1081-1094.
3	Naidich DP, Bankier AA, MacMahon H, et al. Recommendations for the management of subsolid pulmonary nodules detected at CT: a statement from the Fleischner Society [J]. Radiology, 2013, 266: 304-317.
4	Detterbeck FC, Homer RJ. Approach to the ground-glass nodule [J].Clin Chest Med, 2011, 32(4): 799-810.
5	中华医学会放射学分会心胸学组.肺亚实性结节影像处理专家共识[J].中华放射学杂志, 2015, 49(4): 254-258.
6	Yang L, Dong D, Fang M, et al. Can CT-based radiomics signature predict KRAS/NRAS/BRAF mutations in colorectal cancer? [J]. Eur Radiol, 2018, 28(5): 2058-2067.
7	Wang S, Zhou M, Liu Z, et al. Central focused convolutional neural networks: developing a data-driven model for lung nodule segmentation [J]. Med Image Anal, 2017, 40: 172-183.
8	Digumarthy SR, Padole AM, Gullo RL, et al. CT texture nalysis of histologically proven benign and malignant lung lesions [J]. Medicine (Baltimore), 2018, 97(26): e11172.
9	Areeckal AS, Kamath J, Zawadynski S, et al. Combined radiogrammetry and texture analysis for early diagnosis of osteoporosis using Indian and Swiss data [J]. Comput Med Imaging Graph, 2018, 68: 25-39.
10	Zhou H, Dong D, Chen B, et al. Diagnosis of distant metastasis of lung cancer: based on clinical and radiomic features [J]. Transl Oncol, 2018, 11(1): 31-36.
11	Hwang IP, Park CM, Park SJ, et al. Persistent pure ground-glass nodules larger than 5 mm: differentiation of invasive pulmonary adenocarcinomas from preinvasive lesions or minimally invasive adenocarcinomas using texture analysis [J]. Invest Radiol, 2015, 50(11): 798-804.
12	Chae HD, Park CM, Park SJ, et al. Computerized texture analysis of persistent part-solid ground-glass nodules: differentiation of preinvasive lesions from invasive pulmonary adenocarcinomas [J]. Radiology, 2014, 273(1): 285-293.
13	罗婷，张峥，李昕, 等. CT图像纹理分析鉴别诊断磨玻璃密度肺腺癌的浸润性[J].中国医学影像技术, 2017, 33(12): 1788-1791.
14	李西，肖湘生，于红, 等. CT图像纹理特征分析对肺部纯磨玻璃结节侵袭性的诊断价值[J].山西医药杂志, 2016, 45(12): 1411-1414.
15	范丽，方梦捷，董迪, 等.影像组学对磨玻璃结节型肺腺癌病理亚型的预测效能[J].中华放射学杂志, 2017, 51(12): 912-917.
16	Murakawa T, Konoeda C, Ito T, et al. The ground glass opacity component can be eliminated from the T-factor assessment of lung adenocarcinoma [J]. Eur J Cardiothorac Surg, 2013, 43(5): 925-932.
17	Lee SH, Lee SM, Goo JM, et al. Usefulness of texture analysis in differentiating transient from persistent part-solid nodules (PSNs): a retrospective study [J]. PLoS One, 2014, 9(1): e85167.
18	Jiang B, Wang J, Jia P, et al. The value of CT Attenuation in distinguishing atypical adenomatous hyperplasia from adenocarcinoma in situ [J]. Chin J Lung Cancer, 2013, 16(11): 579-583.
19	Takahashi M, Shigematsu Y, Ohta M, et al. Tumor invasiveness as defined by the newly proposed IASLC/ATS/ERS classification has prognostic significance for pathologic stage IA lung adenocarcinoma and can be predicted by radiologic parameters [J]. J Thorac Cardiovasc Surg, 2014, 147(1): 54-59.
20	Li M, Wu N, Zhang L, et al. Solid component proportion is an important predictor of tumor invasiveness in clinical stage T₁ N₀ M₀ (cT₁ N₀ M₀) lung adenocarcinoma [J]. Cancer Imaging, 2018, 18(1): 18.
21	Matsuguma H, Oki I, Nakahara R, et al. Comparison of three measurements on computed tomography for the prediction of less invasiveness in patients with clinical stage I non-small cell lung cancer [J]. Ann Thorac Surg, 2013, 95(6): 1878-1884.
22	Cohen JG, Reymond E, Medici M, et al. CT-texture analysis of subsolid nodules for differentiating invasive from in-situ and minimally invasive lung adenocarcinoma subtypes [J]. Diagn Interv Imaging, 2018, 99(5): 291-299.

[1]	王月香, 朱亚琼, 陈祥慧, 杨静. 序贯教学法在颈椎超声临床教学中的应用[J]. 中华医学超声杂志（电子版）, 2022, 19(06): 548-553.
[2]	王亚萍, 樊菁, 侯牛牛, 凌瑞. 肿瘤浸润性淋巴细胞在HER-2阳性早期乳腺癌中的临床意义[J]. 中华乳腺病杂志(电子版), 2023, 17(04): 203-209.
[3]	韩春颖, 王婷婷, 李艳艳, 朴金霞. 子宫内膜癌患者淋巴管间隙浸润预测因素研究现状[J]. 中华妇幼临床医学杂志(电子版), 2023, 19(04): 403-409.
[4]	董双, 李晓莹, 孙立涛, 田家玮. 影像学技术在宫颈癌术前临床分期中的应用进展[J]. 中华妇幼临床医学杂志(电子版), 2023, 19(01): 113-119.
[5]	马帅, 袁新宇, 辛海燕, 孙晶然, 吕艳玲, 赵华, 杨洋. 影像学检查对儿童化脓性骶髂关节炎的辅助诊断价值[J]. 中华妇幼临床医学杂志(电子版), 2023, 19(01): 100-106.
[6]	王晓燕, 肖佑, 肖戈, 王真权. 老年结直肠癌肺转移CT特征及高危因素研究[J]. 中华普外科手术学杂志(电子版), 2023, 17(05): 506-509.
[7]	张泽华, 杨诗怡, 熊茂明, 张嘉炜. 腹盆腔脂肪与肌肉含量与Miles术后发生造口旁疝风险的相关性研究[J]. 中华疝和腹壁外科杂志(电子版), 2023, 17(01): 9-14.
[8]	郭宏坤, 孟岩, 马自达, 孙少川, 孙中伟. 腹横肌的CT解剖学及其在腹横肌平面阻滞的临床意义[J]. 中华疝和腹壁外科杂志(电子版), 2022, 16(06): 640-643.
[9]	刘立业, 赵德芳. 非酒精性脂肪肝患者血清细胞因子信号转导抑制因子3、肝X受体α水平与CT影像学特征的相关性[J]. 中华消化病与影像杂志(电子版), 2023, 13(04): 211-215.
[10]	黄文鹏, 刘晨晨, 侯佳蒙, 李莉明, 侯平, 肖晓燕, 高剑波. 眼部恶性多形性腺瘤43例临床病理及CT/MRI影像分析[J]. 中华消化病与影像杂志(电子版), 2023, 13(01): 5-9.
[11]	黄文鹏, 李莉明, 曲利媛, 刘剑利, 许歌, 高剑波. 原发性胃淋巴上皮瘤样癌的临床影像分析[J]. 中华消化病与影像杂志(电子版), 2022, 12(06): 351-356.
[12]	韩雷, 陈小宇, 王楠楠. 人工智能与放射科医师判读肺实性肿块CT征象的一致性研究[J]. 中华消化病与影像杂志(电子版), 2022, 12(06): 348-350.
[13]	黄文鹏, 高歌, 邱永康, 杨琦, 陈钊, 康磊, 高剑波. 肠道尤文肉瘤/原发性神经外胚层肿瘤三例并文献复习[J]. 中华消化病与影像杂志(电子版), 2022, 12(05): 296-301.
[14]	陈雪芬, 邓静敏. 国内外179例原发性肺淋巴上皮瘤样癌的文献复习[J]. 中华临床医师杂志(电子版), 2023, 17(05): 551-556.
[15]	牛文博, 吴凤鹏, 刘月平, 周超熙, 张娟, 胡旭华, 李保坤, 王贵英. 新辅助放化疗对局部进展期直肠癌疗效及肿瘤免疫微环境变化的研究[J]. 中华临床医师杂志(电子版), 2023, 17(05): 519-523.

阅读次数

全文

摘要

选择文件类型/文献管理软件名称

选择包含的内容

CT texture analysis in diagnosis of invasiveness of lung adenocarcinoma manifesting as pure ground glass nodules less than 10 mm

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

CT texture analysis in diagnosis of invasiveness of lung adenocarcinoma manifesting as pure ground glass nodules less than 10 mm